GenAI Software Development Engineer

Job Title

GenAI Software Development Engineer

Role Summary

Build and operate an AI-native platform that runs autonomous agent-based hardware validation campaigns, triages failures, and grows a shared knowledge base without human intervention. The role sits in Global Cluster Engineering and focuses on LLM agent frameworks, RAG pipelines, MCP backend, developer tooling, and scalable AI services. AMD is hiring multiple senior engineers for this team.

Experience Level

Senior-level (posting seeks Senior Software Engineers). Specific years of experience are not stated.

Responsibilities

Deliver software components and tooling that enable autonomous AI-driven validation and platform integrations.

• Design, build, and maintain multi-agent orchestration: dispatch, context management, inter-agent communication, progress tracking, and crash recovery.
• Develop and improve RAG pipelines: document ingestion (Slack, GitHub, Jira, Confluence), chunking, embeddings, vector + keyword search, reranking, and knowledge graph indexing.
• Implement scalable, low-latency AI services for metadata generation, feature extraction, and retrieval.
• Build developer-facing web applications and UIs (React/Next.js/Angular/Vue or similar) for observability, validation workflows, and tooling.
• Design and operate backend services: APIs, event-driven architectures, microservices, and integrations with platform systems.
• Create LLM-powered developer tooling: automated test-plan generation, failure triage, knowledge curation, and report generation.
• Ensure security, data privacy, and credential handling across LLM integrations and pipelines.
• Own features end-to-end: estimation, architecture, implementation, deployment, monitoring, and post-launch measurement.
• Participate in operational excellence: CI/CD, IaC (Terraform), monitoring, on-call rotation, and root-cause analysis.
• Collaborate with validation engineers and hardware teams to translate domain requirements into software and onboard new teams.

Requirements

Must-have technical skills and experience to perform the role; preferred qualifications follow.

• Proven software development experience with production systems and end-to-end ownership.
• Experience building LLM-powered systems and AI-native software: grounding, evaluation, failure-mode mitigation, and prompt/context management.
• Hands-on experience building RAG pipelines: embeddings, vector databases, chunking strategies, hybrid search, and reranking.
• Production experience with LLM tool use, multi-agent orchestration, and prompt engineering.
• Strong proficiency in one or more: Python (preferred), TypeScript/Node.js, Go, Java, C#, or Rust; ability to build and operate production-scale services.
• Engineering fundamentals: async programming, API design, distributed systems, reliability, state management, observability, and clean code practices.
• Cloud infrastructure experience (AWS, Azure, or GCP): provisioning, managed services, networking, and deployment at scale.
• Experience with CI/CD pipelines, infrastructure-as-code (e.g., Terraform), automated testing, and monitoring.
• Familiarity with web application development for developer UX and observability dashboards.
• Security and compliance awareness for AI/ML systems, including data protection and credential handling.
• This role is not eligible for visa transfer or sponsorship.

Nice-to-have:

• Experience with Model Context Protocol (MCP) or agentic platforms (Claude Code, LangGraph, CrewAI, AutoGen).
• Familiarity with knowledge graph systems (Neo4j, LightRAG) or graph-augmented RAG.
• Background in semiconductor, datacenter, or networking domains and hardware validation workflows.
• Exposure to Slack, GitHub, or Atlassian APIs; data pipeline or analytics experience.

Education Requirements

BS or MS degree in Computer Science, Electrical Engineering, or a related field.

About the Company

Company: Advanced Micro Devices

Headquarters: Sunnyvale, California, USA

Advanced Micro Devices, or AMD, is a global semiconductor company that designs and manufactures microprocessors, graphics processors, and related technologies for a variety of computing devices. Known for pushing the boundaries of innovation, AMD's mission is to deliver high-performance computing solutions for AI, data centers, gaming, and embedded applications. They foster a collaborative, inclusive culture focused on creativity and problem-solving, aiming to drive progress and excellence in technology.